Get the latest tech news
MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
Novel view synthesis via feed-forward 3D Gaussian inference from sparse multi-view images.
We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. On the large-scale RealEstate10K and ACID benchmarks, MVSplat achieves state-of-the-art performance with the fastest feed-forward inference speed (22 fps). More impressively, compared to the latest state-of-the-art method pixelSplat, MVSplat uses 10× fewer parameters and infers more than 2× faster while providing higher appearance and geometry quality as well as better cross-dataset generalization.
Or read this on Hacker News